Machine learning for defect phases (A07*)

• Subject Area: Computer-Aided Design of Materials and Simulation of Materials Behaviour from Atomic to Microscopic Scale
• Term: since 2024
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 409476157

The aim of the project, together with C02 as its experimental partner, is to make EBSD usable on the size scale between high-resolution and property measurement specifically for research on defect phases. The project will build a library of simulated EBSD patterns for training networks and identifying patterns associated with experimental samples. The project will also explore how machine learning can significantly improve EBSD analysis methods and integrate the TimePix chip’s measurements of electron energy into EBSD pattern analysis.

• DFG Programme: Collaborative Research Centres
• Subproject of: SFB 1394: Structural and Chemical Atomic Complexity: From Defect Phase Diagrams to Material Properties
• Applicant Institution: Rheinisch-Westfälische Technische Hochschule Aachen
• Project Head: Professor Dr. Ulrich Kerzel